DETAILED ACTION
Claims 1-20 are presented for examination. Claims 1 and 11 stand currently amended.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 10 February 2026 has been entered.
Response to Arguments
Applicant's remarks filed 10 February 2026 have been fully considered and Examiner’s response is as follows:
Applicant remarks pages 11-12 argues:
Neither the above nor any other passage of Wong teaches or suggests the above recited subject matter of claim 1. Rather than identifying "one or more operating conditions by comparing ... a current measured value to a corresponding prior value recorded in a database and corresponding to the one or more prior operating conditions," Wong just detects an abnormal fault condition based on a context vector not matching a classification or a cluster in a context vector space. (See, Wong, par. [0026]). Detecting conditions based on context vectors not matching classifications or clusters in a vector space is simply not same as comparing, for each selected state parameter, a current measured value to a corresponding prior value recorded in a database and corresponding to the one or more prior operating conditions. Since Wong operates in a learned vector space, Wong does not teach or suggest comparing any value to a corresponding recorded prior value. Instead, any alleged comparison of Wong is limited only to Wong's learned space which is based on aggregate representations of other values, precluding Wong from comparing any value to a corresponding prior recorded value in such a vector space.
(Underline added.)
The same teaching of the detecting an abnormal fault condition correspondingly teaches determining a normal operating condition (i.e. the absence of an abnormal fault condition). The respective state (abnormal or normal) is itself an operating condition. Therefore, Wong teaches identification of an operating condition.
Regarding the newly recited claim language “comparing, for each selected state parameter” Wong paragraph 24 last sentence teaches “determining cluster membership based on a vector distance measure.” A vector distance measure is a comparison of the distances for each respective element of the vector. Without loss of generality, the parameters of the context vector are the selected parameters.
Applicant remarks pages 12-13 further argues:
Wong also does not teach or suggest "to determine a match in response to a difference between the current measured value and the corresponding prior value not exceeding more than a user-defined threshold." Instead, Wong does the opposite - detects a condition based on a context vector not matching one of the identified classifications or clusters and/or based on a distance of the context vector to a nearest identified cluster exceeding a threshold. Since Wong is focused on identifying abnormalities, Wong is interested only with differences exceeding the threshold, rather than differences not exceeding more than a user-defined threshold. Chan, Curl and Wong alone or in any combination do not teach or suggest at least the above recited subject matter of claim 1, and withdrawal of this rejection of claim 1 and claims 2-10 that depend therefrom is requested for this additional reason as well.
Examiner respectfully disagrees. Detecting whether or not the difference exceeds a threshold is a determination of both conditions where it is exceeded and where it is not exceeded. The condition being tested is the same in each case, only the result and subsequent steps are different. In particular, Wong paragraph 26 teaches:
Preferably, identifying an operating condition comprises detecting an abnormal operating condition (e.g. a fault condition) based on the context vector not matching one of the identified classifications or clusters and/or based on a distance of the context vector to a nearest identified cluster exceeding a threshold distance
The identified cluster for an operating condition is determining a respective match in response to a difference between a current value and prior values (of the cluster). Wong paragraph 24 last sentence teaches “determining cluster membership based on a vector distance measure.” A vector distance measure is a comparison of the distances for each respective element of the vector. Without loss of generality, the parameters of the context vector are the selected parameters.
The choice of Wong to describe the determinations according to being normal or abnormal does not change the threshold comparison being performed. Furthermore, Wong paragraph 70 teach “a determination as to whether the detected operating state corresponds to a normal operating step in step 412.” Thus, Wong also teaches explicitly determining normal operating.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-20
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over US 2020/0387818 A1 Chan, et al. [herein “Chan”] in view of Curl, J., et al. “Digital Twins: The Next Generation of Water Treatment Technology” J. Am. Water Works Ass., vol. 111, issue 12, pp. 44-50 (2019) [herein “Curl”], and US 2020/0371491 A1 Wong [herein “Wong”].
Claim 1 recites “1. A system to adjust operation of a plant.” Chan title discloses “Asset optimization.” Chan abstract last sentence discloses “deployed online to perform asset optimization tasks in real-time plant operations.” Chan paragraph 72 discloses “real-time process control and optimization implementation.” Control corresponds with respective adjustment.
Claim 1 further recites “comprising: a data processing system having at least one processor coupled with memory.” Chan figure 6 shows a “central processor unit 84” and “memory 90.” See further Chan paragraph 162.
Claim 1 further recites “to: provide a prompt to adjust of a performance of a plant indicating a plurality of performance indicators in a model of the plant.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Chan paragraph 11 lines 17-18 disclose “a user defined key performance indicator.” User defined corresponds with being received from selected by the user.
Claim 1 further recites “receive data from a plurality of physical instruments monitoring operation of a plurality of assets for treatment of liquid at the plant, the data comprising a real-time measurement of a parameter indicative of an operation for treatment of liquid.” Chan paragraph 121 disclose “receives real-time input measurements from plant sensors.” Receiving real-time input from sensors corresponds with receiving real-time measurement data from physical instruments of the plant.
Chan does not explicitly disclose a liquid treatment; however, in analogous art of digital twin optimization, Curl page 44 first “key takeaway” teaches “Water utilities are turning to ‘digital twins’ to benefit their ongoing operations, improve planning, and enhance operator training.” Curl page 46 left column fourth paragraph states “How does a digital twin work within the context of a water treatment facility” summarizing the question answered in the remainder of the article. Using a digital twin with a water treatment facility corresponds with data processing optimization for water treatment at a plant.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chan and Curl. One having ordinary skill in the art would have found motivation to use modeling a water treatment facility into the system of asset optimization for the advantageous purpose of “benefit their ongoing operations, improve planning, and enhance operator training.” See Curl page 44 and see further Curl page 46 section “Benefits of Digital Twins.”
Claim 1 further recites “and a selection, via the prompt, of a performance indicator of the plurality of performance indicators for the parameter of the operation for treatment of liquid to adjust in accordance with a set-point of an asset of the plurality of assets for treatment of liquid at the plant.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Chan paragraph 11 lines 17-18 disclose “a user defined key performance indicator.” User defined corresponds with being received from selected by the user.
Chan does not explicitly disclose a liquid treatment; however, in analogous art of digital twin optimization, Curl page 44 first “key takeaway” teaches “Water utilities are turning to ‘digital twins’ to benefit their ongoing operations, improve planning, and enhance operator training.” Curl page 46 left column fourth paragraph states “How does a digital twin work within the context of a water treatment facility” summarizing the question answered in the remainder of the article. Using a digital twin with a water treatment facility corresponds with data processing optimization for water treatment at a plant.
Claim 1 further recites “generate, via the model and based on the data and a plurality of test values for the set-point, a plurality of values for the performance indicator selected via the prompt.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Generated KPIs from model prediction correspond with generated performance indicator values via a model.
Chan paragraph 11 lines 17-18 disclose “a user defined key performance indicator.” User defined corresponds with being received from selected by the user.
Claim 1 further recites “wherein the model is trained using historical data of the plurality of assets for treatment of liquid to identify correlation between the plurality of parameters and set point adjustments of the plurality of assets at the plant.” Chan paragraph 40 discloses “hybrid models built from historical data with the help of AI and ML can be deployed online for real-time optimization with less efforts.” Building an AI/machine learning model from historical data is training a model using historical data.
Chan paragraph 108 discloses “The cross-correlation analysis facilitates identifying and grouping highly correlated inputs (including both measurements of process variables and values of derived feature variables) in the cleansed/enriched dataset.” Identifying inputs correlated with derived feature variables corresponds with identifying correlations between input parameter process variables and operation of respective assets at the plant.
Claim 1 further recites “determine one or more settings for one or more set-points of at least one of the plurality of assets at the plant based on the plurality of values for the performance indicator and the plurality of test values for the set-point.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Operating the plant at an operating condition corresponds with determining respective settings for that operating condition based on those generated KPIs.
Chan paragraph 40 discloses “In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset.” Optimal operation setpoints correspond with determined settings for setpoints.
Claim 1 further recites “wherein the one or more settings are determined by a correlation of (i) the set-point and the values for the performance indicator.” Chan paragraph 108 discloses “The cross-correlation analysis facilitates identifying and grouping highly correlated inputs (including both measurements of process variables and values of derived feature variables) in the cleansed/enriched dataset.” Identifying inputs correlated with derived feature variables corresponds with identifying correlations between input parameter process variables (i.e. set-points) and derived feature variables (i.e. performance indicators).
Claim 1 further recites “wherein the one or more settings are determined by a correlation of … (ii) current state parameters indicative of current conditions at the plant, and (iii) historical state parameters indicative of one or more prior operating conditions at the plant, with the one or more set-points that satisfy one or more constraints.” Chan paragraph 108 discloses “The cross-correlation analysis facilitates identifying and grouping highly correlated inputs (including both measurements of process variables and values of derived feature variables) in the cleansed/enriched dataset.” Identifying inputs correlated with derived feature variables corresponds with identifying respective correlations.
Chan paragraph 84 discloses “Where X contains all manipulate and state variables, and Y represents one or more dependent variables, θ is a vector of model parameters.” Accordingly, the input process variables correspond with state parameters. Chan paragraph 90 discloses “loads historical and real-time operations data (measurements) for process variables of the subject plant process from a plant historian or asset database.” The real-time operations data corresponds with current state parameters. The historical operations data corresponds with prior operating conditions.
Chan paragraph 40 discloses “In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset.” Optimal operation setpoints correspond with determined settings for setpoints. Chan paragraph 140 disclose “A model may have many process parameters (e.g., a number of process variables or process constraints) that represent the status of an industrial process.” Process constraints correspond with satisfying respective set-point constraints.
Claim 1 further recites “and provide the one or more settings for the one or more set-points to control the plurality of assets for treatment of liquid at the plant and adjust the performance of the plant.” Chan paragraph 157 discloses “The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404.” Providing input to adjust parameters for the control system corresponds with providing one or more settings to adjust performance of the plant to control the various assets of the system.
Claim 1 further recites “wherein the data processing system is configured to: (i) identify, for a set of one or more selected state parameters, one or more prior operating conditions by comparing, for each selected state parameter, a current measured value to a corresponding prior value recorded in a database and corresponding to the one or more prior operating conditions, to determine a match in response to a difference between the current measured value and the corresponding prior value not exceeding a user-defined threshold.” Chan paragraph 119 disclose “At step 130-2, the embodiments can enrich the base-model by embedding some AI/ML techniques, such as clustering and classification algorithms.” Chan figure 3G “compare case” teaches “identify closest cluster” See further Chan paragraph 143. Clustering is identifying respective sets of parameters which differ by no more than a defined threshold.
Chan paragraph 120 section heading discloses “Deploy Model Online (140).” Chan paragraph 123 disclose:
These models may compare the current real-time data of the subject plant process to pre-defined performance criterions from historical data of the subject plant process. Based on the comparison, one or more models detect whether degradation in performance conditions appeared in the subject plant process.
Comparing real-time data with historical data of the plant is identifying current operating values which differ from prior operating conditions. However, Chan paragraph 123 is a comparison of the performance criteria, not a comparison of respective operating conditions.
But Chan does not explicitly disclose comparing for each selected state parameter; however, in analogous art of analyzing an industrial process, Wong paragraph 26 teaches:
Preferably, identifying an operating condition comprises detecting an abnormal operating condition (e.g. a fault condition) based on the context vector not matching one of the identified classifications or clusters and/or based on a distance of the context vector to a nearest identified cluster exceeding a threshold distance
The identified cluster for an operating condition is determining a respective match in response to a difference between a current value and prior values (of the cluster). Wong paragraph 24 last sentence teaches “determining cluster membership based on a vector distance measure.” A vector distance measure is a comparison of the distances for each respective element of the vector. Without loss of generality, the parameters of the context vector are the selected parameters.
Wong paragraph 70 teach “a determination as to whether the detected operating state corresponds to a normal operating step in step 412.”
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chan, Curl, and Wong. One having ordinary skill in the art would have found motivation to use clustering with distance detection into the system of asset optimization for the advantageous purpose of implementing “could implement automatic control actions in response to specific detected operating states.” See Wong ¶ 72.
Claim 1 further recites “and (ii) select, from set-point values recorded in the database and used during the one or more prior operating conditions, a set-point value applied during the one or more prior operating conditions that resulted in values of the performance indicator to adjust the performance of the plant.” Chan paragraph 157 discloses:
The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404. … The Instrumentation, Control, Operation Computer 405, based on the input, may then automatically adjust or program (via network 408) physical valves, actuators, heaters, and the like 409A-409I, or program any other plant or refinery control system or processing system coupled to the DCS system 404, to execute the calculated PSE solution in the plant process.
Automatically adjust physical valves, actuators, heaters, and the like corresponds with an adjustment to the performance of the plant. The respectively provided input corresponds with selected set-point values.
Chan paragraph 40 disclose:
In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset. …hybrid models built from historical data with the help of AI and ML can be deployed online for real-time optimization with less efforts. These models satisfy the requirement of conforming to historical data.
A set of optimal operation setpoints are selected set point values. The models conforming to the historical data is the selected set point values corresponding with historical data operations.
Furthermore, Wong paragraph 70 and figure 4 teach “a determination as to whether the detected operating state corresponds to a normal operating step in step 412.” The normal operating correspond to identified operating states within a threshold distance for the operating condition as discussed above regarding Wong ¶26. Thus, respective automatic adjustments are of those values from the identified normal operating values when a normal operating is detected.
Claim 2 further recites “2. The system of claim 1, comprising the data processing system to: receive, via the prompt, a selection of one or more constraints for the set-point; and generate the plurality of values for the performance indicator via the model and based on the plurality of test values for the set-point within the one or more constraints of the set-point.” Chan paragraph 83 discloses “The complex relations linking all three kind of process variables are represented in a model, and all relevant physical and chemical operating boundaries can be formulated as constraints equations.” Constraint equations correspond with constraints for the process variables and their setpoints.
Claim 3 further recites “3. The system of claim 1, comprising the data processing system to: provide the one or more settings for the one or more set-points to adjust operation of the at least one of the plurality of assets at the plant.” Chan paragraph 157 discloses “The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404.” Providing input to adjust parameters for the control system corresponds with providing one or more settings to adjust performance of the plant.
Claim 3 further recites “and display the one or more settings for the one or more set-points and adjusted performance of the plant determined based on the settings for the one or more set-points input into the model.” Chan paragraph 122 discloses:
helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition. For example, the plant user or system may use the KPIs to indicate current status in the subject plant process, such as process throughput, energy consumptions, product quality, profit margins, and such.
Indicating a current status of KPIs and monitoring an optimal operation condition corresponds with displaying the optimized performance of the plant. Chan paragraph 157 discloses “The model execution module 440 may also provide operation status and optimization results to the user interface 401 for presentation to the user.” Providing operation status and results for presentation to a user is displaying respective settings and performance based on those settings.
Claim 4 further recites “4. The system of claim 1, comprising the data processing system to select, based on an input by a user, the model of the plant from a plurality of models for a plurality of plants, the model of the plant modeling operation of the plurality of assets at the plant.” Chan paragraph 6 discloses “a configuration module to automatically select a model type for the model development module to build and train the process model.” Chan paragraph 88 discloses “user to examine feasibility and validate the selected model type at step 110-2 and model built at step 110-3.” The user validating the selected model type corresponds with the system selecting the model of the plant based on user input. See also Chan ¶ 67.
Chan paragraph 106 discloses “the method 120-3 then requests a user to select engineering transform equations, or uses default engineering transform equations for a specific process unit.” The engineering transform equations correspond with the modeling. Accordingly, the user selecting the transform equations or using default engineering transform equations is selecting, based on user input, the model for the plant. The respective default transform equations correspond with a plurality of models
Claim 5 further recites “5. The system of claim 1, comprising the data processing system to: receive selection of two or more performance indicators of the plurality of performance indicators, two or more set-points for at least two or more the plurality of assets and two or more constraints for the two or more set-points.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Plural indicators are two or more performance indicators.
Chan paragraph 83 discloses “The complex relations linking all three kind of process variables are represented in a model, and all relevant physical and chemical operating boundaries can be formulated as constraints equations.” Constraint equations correspond with constraints for the process variables and their setpoints.
Claim 5 further recites “generate the plurality of values for the two or more performance indicators via the model and based on the data and the plurality of test values for the two or more set-points within two or more constraints for the two or more set-points.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Generated KPIs from model prediction correspond with generated performance indicator values via a model.
Claim 5 further recites “and determine two or more settings for the two or more set-points based on the plurality of values for the two or more performance indicators and the plurality of test values for the two or more set-points.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Operating the plant at an operating condition corresponds with determining respective settings for that operating condition based on those generated KPIs.
Chan paragraph 40 discloses “In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset.” Optimal operation setpoints correspond with determined settings for setpoints. A set of optimal operation setpoints (plural) is two or more.
Claim 6 further recites “6. The system of claim 1, comprising the data processing system to: receive, via a real-time data stream, updated data from the plurality of physical instruments.” Chan paragraph 121 disclose “receives real-time input measurements from plant sensors.” Receiving input from sensors corresponds with receiving data from physical instruments of the plant.
Claim 6 further recites “generate an updated plurality of values for the performance indicator via the model and based on the updated data and the plurality of test values for the set-point.” Chan paragraph 122 discloses “From the real-time measurements and derived feature variables' values, the process model may generate current estimates of important product properties, in a format of continuous key performance indicators (KPIs).” Deriving feature values from the real-time measurements to generate current estimates of KPIs corresponds with generating updated values for the performance indicators via the model based on the updated data.
Claim 6 further recites “determine one or more updated settings for one or more set-points of at least one of the plurality of assets at the plant based on the updated plurality of values for the performance indicator and the plurality of test values for the set-point.” Chan paragraph 63 discloses:
(11) The system monitors its performance while generating predictions and solutions, and can perform model adaptions when model predictions and solutions become sub-optimal. In such a way, the system keeps its model and solutions updated and ensures a sustained performance.
Keeping solutions updated corresponds with determining updated settings. The solutions correspond with the settings.
Claim 6 further recites “and provide the one or more updated settings for the one or more set-points to adjust the performance of the plant.” Chan paragraph 157 discloses “The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404.” Providing input to adjust parameters for the control system corresponds with providing one or more settings to adjust performance of the plant.
Claim 7 further recites “7. The system of claim 1, comprising the data processing system to: preprocess the data from the plurality of physical instruments; and receive data comprising the preprocessed data from the plurality of physical instruments.” Chan paragraph 69 discloses:
(4) Repair missing and bad quality data: The system provides flexibility for user to pre-process data with several processing options: (a) Interpolation-fill in data gaps with interpolation; (b) Filtering-applying non-phaseshift filters to selected noisy process measurements for data smoothing; (c) Model based data repairing-replace outliers, gaps and other identified bad data segments with internal model produced values; and (d) Resampling data-upsample original time-series data with snapshots or average as options, or down-sample data with interpolated values.
Claim 8 further recites “8. The system of claim 1, comprising the data processing system to: train a learning optimization function using the data; and determine the one or more settings for one or more set-points of at least one of the plurality of assets at the plant further based on the learning optimization function.” Chan paragraph 71 discloses “a ‘hyper-plan’ ML approximation model may be appropriate, which is trained from plant operation data and simulated data.” Training from operation data corresponds with training a learning optimization function using data. See further Chan paragraph 172.
Claim 9 further recites “9. The system of claim 1, comprising the data processing system to: receive, via the prompt, data from the plurality of physical instruments monitoring operation of the plurality of assets for water treatment at the plant.” Chan paragraph 121 disclose “receives real-time input measurements from plant sensors.” Receiving input from sensors corresponds with receiving data from physical instruments of the plant.
Chan paragraph 1 discloses “Chemical and petrochemical manufacturers.”
Chan does not explicitly disclose a water treatment plant; however, in analogous art of digital twin optimization, Curl page 44 first “key takeaway” teaches “Water utilities are turning to ‘digital twins’ to benefit their ongoing operations, improve planning, and enhance operator training.” Curl page 46 left column fourth paragraph states “How does a digital twin work within the context of a water treatment facility” summarizing the question answered in the remainder of the article. Using a digital twin with a water treatment facility corresponds with data processing optimization for water treatment at a plant.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chan and Curl. One having ordinary skill in the art would have found motivation to use modeling a water treatment facility into the system of asset optimization for the advantageous purpose of “benefit their ongoing operations, improve planning, and enhance operator training.” See Curl page 44 and see further Curl page 46 section “Benefits of Digital Twins.”
Claim 9 further recites “and provide the one or more settings for the one or more set-points to adjust the performance of the one or more assets for water treatment at the plant.” Chan paragraph 157 discloses “The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404.” Providing input to adjust parameters for the control system corresponds with providing one or more settings to adjust performance of the plant.
Claim 10 further recites “10. The system of claim 9, comprising the data processing system to: receive, via the prompt, the selection of the performance indicator for one or more of a reverse osmosis recovery rate and a reverse osmosis energy consumption to adjust in accordance with the set-point for one of a fluid pump operation, a valve operation, a fluid pressure and a reverse osmosis product flow.” From the above list of alternatives the Examiner is selecting “a valve operation.”
Chan paragraph 149 discloses “manipulated input variables, such as reflux flow rate as set by valve 409F … and pressure in a column as controlled by a valve 409G.” Chan paragraph 161 discloses “measurement control devices (valves, actuators, heaters, and the like 409A-I) for adjusting a plant process.” Control of a valve for adjusting a plant process corresponds with a valve operation indicator.
Claim 10 further recites “and provide the one or more settings for the one or more set-points to adjust the one of the reverse osmosis recovery rate and the reverse osmosis energy consumption of the plant.” Chan paragraph 161 discloses “measurement control devices (valves, actuators, heaters, and the like 409A-I) for adjusting a plant process.”
Claim 11 recites “11. A method adjusting operation of a plant.” Chan title discloses “Asset optimization.” Chan abstract last sentence discloses “deployed online to perform asset optimization tasks in real-time plant operations.” Chan paragraph 72 discloses “real-time process control and optimization implementation.” Control corresponds with respective adjustment.
Claim 11 recites the “data processing system” a plurality of times including “comprising: providing, by a data processing system comprising memory and one or more processors.” Chan figure 6 shows a “central processor unit 84” and “memory 90.” See further Chan paragraph 162.
Claim 11 further recites “comprising: providing, …, a prompt for adjusting a performance of a plant indicating a plurality of performance indicators in a model of the plant.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Chan paragraph 11 lines 17-18 disclose “a user defined key performance indicator.” User defined corresponds with being received from selected by the user.
Claim 11 further recites “receiving, …, data from a plurality of physical instruments monitoring operation of a plurality of assets for treatment of liquid at the plant, the data comprising a real-time measurement of a parameter indicative of an operation for treatment of liquid.” Chan paragraph 121 disclose “receives real-time input measurements from plant sensors.” Receiving real-time input from sensors corresponds with receiving real-time measurement data from physical instruments of the plant.
Chan does not explicitly disclose a liquid treatment; however, in analogous art of digital twin optimization, Curl page 44 first “key takeaway” teaches “Water utilities are turning to ‘digital twins’ to benefit their ongoing operations, improve planning, and enhance operator training.” Curl page 46 left column fourth paragraph states “How does a digital twin work within the context of a water treatment facility” summarizing the question answered in the remainder of the article. Using a digital twin with a water treatment facility corresponds with data processing optimization for water treatment at a plant.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chan and Curl. One having ordinary skill in the art would have found motivation to use modeling a water treatment facility into the system of asset optimization for the advantageous purpose of “benefit their ongoing operations, improve planning, and enhance operator training.” See Curl page 44 and see further Curl page 46 section “Benefits of Digital Twins.”
Claim 11 further recites “and a selection, via the prompt, of a performance indicator of the plurality of performance indicators for the parameter of the operation for treatment of liquid to adjust in accordance with a set-point of an asset of the plurality of assets for treatment of liquid at the plant.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Chan paragraph 11 lines 17-18 disclose “a user defined key performance indicator.” User defined corresponds with being received from selected by the user.
Chan does not explicitly disclose a liquid treatment; however, in analogous art of digital twin optimization, Curl page 44 first “key takeaway” teaches “Water utilities are turning to ‘digital twins’ to benefit their ongoing operations, improve planning, and enhance operator training.” Curl page 46 left column fourth paragraph states “How does a digital twin work within the context of a water treatment facility” summarizing the question answered in the remainder of the article. Using a digital twin with a water treatment facility corresponds with data processing optimization for water treatment at a plant.
Claim 11 further recites “generating, …, via the model and based on the data and a plurality of test values for the set-point, a plurality of values for the performance indicator selected via the prompt.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Generated KPIs from model prediction correspond with generated performance indicator values via a model.
Chan paragraph 11 lines 17-18 disclose “a user defined key performance indicator.” User defined corresponds with being received from selected by the user.
Claim 11 further recites “wherein the model is trained using historical data of the plurality of assets for treatment of liquid to identify correlation between the plurality of parameters and set point adjustments of the plurality of assets at the plant.” Chan paragraph 40 discloses “hybrid models built from historical data with the help of AI and ML can be deployed online for real-time optimization with less efforts.” Building an AI/machine learning model from historical data is training a model using historical data.
Chan paragraph 108 discloses “The cross-correlation analysis facilitates identifying and grouping highly correlated inputs (including both measurements of process variables and values of derived feature variables) in the cleansed/enriched dataset.” Identifying inputs correlated with derived feature variables corresponds with identifying correlations between input parameter process variables and operation of respective assets at the plant.
Claim 11 further recites “determining, …, one or more settings for one or more set-points of at least one of the plurality of assets at the plant based on the plurality of values for the performance indicator and the plurality of test values for the set-point.” Chan paragraph 122 discloses:
important product properties, in a format of continuous key performance indicators (KPIs) used as indicators of the process operation over time. The generated KPIs from model prediction can be very important and helpful for a plant user (e.g., process engineer/operator) or plant system to monitor and maintain the operations of the subject plant process at a safe and optimal operation condition.
Operating the plant at an operating condition corresponds with determining respective settings for that operating condition based on those generated KPIs.
Chan paragraph 40 discloses “In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset.” Optimal operation setpoints correspond with determined settings for setpoints.
Claim 11 further recites “wherein the one or more settings are determined by a correlation of (i) the set-point and the values for the performance indicator.” Chan paragraph 108 discloses “The cross-correlation analysis facilitates identifying and grouping highly correlated inputs (including both measurements of process variables and values of derived feature variables) in the cleansed/enriched dataset.” Identifying inputs correlated with derived feature variables corresponds with identifying correlations between input parameter process variables (i.e. set-points) and derived feature variables (i.e. performance indicators).
Claim 11 further recites “wherein the one or more settings are determined by a correlation of … “(ii) current state parameters indicative of current conditions at the plant, and (iii) historical state parameters indicative of one or more prior operating conditions at the plant, with the one or more set-points that satisfy one or more constraints.” Chan paragraph 108 discloses “The cross-correlation analysis facilitates identifying and grouping highly correlated inputs (including both measurements of process variables and values of derived feature variables) in the cleansed/enriched dataset.” Identifying inputs correlated with derived feature variables corresponds with identifying respective correlations.
Chan paragraph 84 discloses “Where X contains all manipulate and state variables, and Y represents one or more dependent variables, θ is a vector of model parameters.” Accordingly, the input process variables correspond with state parameters. Chan paragraph 90 discloses “loads historical and real-time operations data (measurements) for process variables of the subject plant process from a plant historian or asset database.” The real-time operations data corresponds with current state parameters. The historical operations data corresponds with prior operating conditions.
Chan paragraph 40 discloses “In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset.” Optimal operation setpoints correspond with determined settings for setpoints. Chan paragraph 140 disclose “A model may have many process parameters (e.g., a number of process variables or process constraints) that represent the status of an industrial process.” Process constraints correspond with satisfying respective set-point constraints.
Claim 11 further recites “and providing, …, the one or more settings for the one or more set-points to control the plurality of assets for treatment of liquid at the plant and adjust the performance of the plant.” Chan paragraph 157 discloses “The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404.” Providing input to adjust parameters for the control system corresponds with providing one or more settings to adjust performance of the plant to control the various assets of the system.
Claim 11 further recites “wherein the data processing system is configured to: (i) identify, for a set of one or more selected state parameters, one or more prior operating conditions by comparing, for each selected state parameter, a current measured value to a corresponding prior value recorded in a database and corresponding to the one or more prior operating conditions, to determine a match in response to a difference between the current measured value and the corresponding prior value not exceeding a user-defined threshold.” Chan paragraph 119 disclose “At step 130-2, the embodiments can enrich the base-model by embedding some AI/ML techniques, such as clustering and classification algorithms.” Chan figure 3G “compare case” teaches “identify closest cluster” See further Chan paragraph 143. Clustering is identifying respective sets of parameters which differ by no more than a defined threshold.
Chan paragraph 120 section heading discloses “Deploy Model Online (140).” Chan paragraph 123 disclose:
These models may compare the current real-time data of the subject plant process to pre-defined performance criterions from historical data of the subject plant process. Based on the comparison, one or more models detect whether degradation in performance conditions appeared in the subject plant process.
Comparing real-time data with historical data of the plant is identifying current operating values which differ from prior operating conditions. However, Chan paragraph 123 is a comparison of the performance criteria, not a comparison of respective operating conditions.
But Chan does not explicitly disclose comparing for each selected state parameter; however, in analogous art of analyzing an industrial process, Wong paragraph 26 teaches:
Preferably, identifying an operating condition comprises detecting an abnormal operating condition (e.g. a fault condition) based on the context vector not matching one of the identified classifications or clusters and/or based on a distance of the context vector to a nearest identified cluster exceeding a threshold distance
The identified cluster for an operating condition is determining a respective match in response to a difference between a current value and prior values (of the cluster). Wong paragraph 24 last sentence teaches “determining cluster membership based on a vector distance measure.” A vector distance measure is a comparison of the distances for each respective element of the vector. Without loss of generality, the parameters of the context vector are the selected parameters.
Wong paragraph 70 teach “a determination as to whether the detected operating state corresponds to a normal operating step in step 412.”
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chan, Curl, and Wong. One having ordinary skill in the art would have found motivation to use clustering with distance detection into the system of asset optimization for the advantageous purpose of implementing “could implement automatic control actions in response to specific detected operating states.” See Wong ¶ 72.
Claim 11 further recites “and (ii) select, from set-point values recorded in the database used during the one or more prior operating conditions, a set-point value applied during the one or more prior operating conditions that resulted in values of the performance indicator to adjust the performance of the plant.” Chan paragraph 157 discloses:
The model execution module 440 may also automatically provide input (adjust parameters/variables/constraints) to the [distributed control system (DCS)] 404. … The Instrumentation, Control, Operation Computer 405, based on the input, may then automatically adjust or program (via network 408) physical valves, actuators, heaters, and the like 409A-409I, or program any other plant or refinery control system or processing system coupled to the DCS system 404, to execute the calculated PSE solution in the plant process.
Automatically adjust physical valves, actuators, heaters, and the like corresponds with an adjustment to the performance of the plant. The respectively provided input corresponds with selected set-point values.
Chan paragraph 40 disclose:
In the case of online optimization, a process optimizer can compare various conditions and calculate a set of optimal operation setpoints to, for example, maximize profits and/or minimize costs of the asset. …hybrid models built from historical data with the help of AI and ML can be deployed online for real-time optimization with less efforts. These models satisfy the requirement of conforming to historical data.
A set of optimal operation setpoints are selected set point values. The models conforming to the historical data is the selected set point values corresponding with historical data operations.
Furthermore, Wong paragraph 70 and figure 4 teach “a determination as to whether the detected operating state corresponds to a normal operating step in step 412.” The normal operating correspond to identified operating states within a threshold distance for the operating condition as discussed above regarding Wong ¶26. Thus, respective automatic adjustments are of those values from the identified normal operating values when a normal operating is detected.
Dependent claims 12-18 are substantially similar to claims 2-8 above and are rejected for the same reasons.
Dependent claims 19 and 20 are substantially similar to claims 9 and 10 above and are rejected for the same reasons.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jay B Hann whose telephone number is (571)272-3330. The examiner can normally be reached M-F 10am-7pm EDT.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Renee Chavez can be reached at (571) 270-1104. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Jay Hann/Primary Examiner, Art Unit 2186 26 February 2026